Search Results for author:
Found 19 papers, 4 papers with code
ST-VLM: Kinematic Instruction Tuning for Spatio-Temporal Reasoning in Vision-Language Models
To bridge this gap, we construct a spatio-temporal reasoning dataset and benchmark involving kinematic instruction tuning, referred to as STKit and STKit-Bench.
Progressive Token Length Scaling in Transformer Encoders for Efficient Universal Segmentation
A powerful architecture for universal segmentation relies on transformers that encode multi-scale image features and decode object queries into mask predictions.
Efficient Transformer Encoders for Mask2Former-style models
The third step is to use the aforementioned derived dataset to train a gating network that predicts the number of encoder layers to be used, conditioned on the input image.
Generating Enhanced Negatives for Training Language-Based Object Detectors
The recent progress in language-based open-vocabulary object detection can be largely attributed to finding better ways of leveraging large-scale data with free-form text annotations.
Efficient Controllable Multi-Task Architectures
Further, we present a simple but effective search algorithm that translates user constraints to runtime width configurations of both the shared encoder and task decoders, for sampling the sub-architectures.
Taming Self-Training for Open-Vocabulary Object Detection
This work identifies two challenges of using self-training in OVD: noisy PLs from VLMs and frequent distribution changes of PLs.
OmniLabel: A Challenging Benchmark for Language-Based Object Detection
With more than 28K unique object descriptions on over 25K images, OmniLabel provides a challenging benchmark with diverse and complex object descriptions in a naturally open-vocabulary setting.
Confidence and Dispersity Speak: Characterising Prediction Matrix for Unsupervised Accuracy Estimation
This work aims to assess how well a model performs under distribution shifts without using labels.
PU GNN: Chargeback Fraud Detection in P2E MMORPGs via Graph Attention Networks with Imbalanced PU Labels
The recent advent of play-to-earn (P2E) systems in massively multiplayer online role-playing games (MMORPGs) has made in-game goods interchangeable with real-world values more than ever before.
Controllable Dynamic Multi-Task Architectures
In contrast to the existing dynamic multi-task approaches that adjust only the weights within a fixed architecture, our approach affords the flexibility to dynamically control the total computational cost and match the user-preferred task importance better.
On Generalizing Beyond Domains in Cross-Domain Continual Learning
Humans have the ability to accumulate knowledge of new tasks in varying conditions, but deep neural networks often suffer from catastrophic forgetting of previously learned knowledge after learning a new task.
Learning Semantic Segmentation from Multiple Datasets with Label Shifts
First, a gradient conflict in training due to mismatched label spaces is identified and a class-independent binary cross-entropy loss is proposed to alleviate such label conflicts.
Cross-Domain Similarity Learning for Face Recognition in Unseen Domains
Intuitively, it discriminatively correlates explicit metrics derived from one domain, with triplet samples from another domain in a unified loss function to be minimized within a network, which leads to better alignment of the training domains.
Learning to Optimize Domain Specific Normalization for Domain Generalization
We propose a simple but effective multi-source domain generalization technique based on deep neural networks by incorporating optimized normalization layers that are specific to individual domains.
Ranked #3 on
Unsupervised Domain Adaptation
on PACS
Stochastic Class-Based Hard Example Mining for Deep Metric Learning
Performance of deep metric learning depends heavily on the capability of mining hard negative examples during training.
Part-Aligned Bilinear Representations for Person Re-identification
We propose a novel network that learns a part-aligned representation for person re-identification.
Ranked #4 on
Person Re-Identification
on UAV-Human
Holistic Planimetric prediction to Local Volumetric prediction for 3D Human Pose Estimation
We propose a novel approach to 3D human pose estimation from a single depth map.
Subgraph Matching Using Compactness Prior for Robust Feature Correspondence
By constructing Markov chain on the restricted search space instead of the original solution space, our method approximates the solution effectively.
